Sakana AI paper: Neural nets can learn well while following biological rules
TheTuringPost · x · 2026-07-31
A recent paper from Sakana AI explores whether artificial neural networks need to follow the brain's Dale's principle (where each neuron is strictly excitatory or inhibitory).
- Methodology: Researchers separated excitatory and inhibitory signals and abandoned standard backpropagation. Instead, they used an Error Diffusion (ED) method, which shares a broad error signal across layers without transporting exact weight copies backward, making it more biologically plausible.
- Results: The network achieved 96.7% accuracy on MNIST and 61.7% on CIFAR-10. It also handled image classification, reinforcement learning, and simulated robot control reasonably well, though falling short of top-tier conventional networks.
- Conclusion: This suggests that biologically plausible learning is possible but not strictly necessary. Much like building airplanes didn't require copying birds exactly, AI might not need a perfect brain replica, though biology can still offer valuable inspirations.
Related event: Sakana AI Explores Biologically-Constrained Neural Networks(3 posts)→
More from Research
- Transforming quadruped robot runs on real hardware: per-pose RL policies in Isaac switched on morph — _Stocko_ · 2026-10-16
- KinoGen synthesizes robot loco-manipulation reference motions directly via kinematically grounded video generation — ChongZzZhang · 2026-10-16
- Science Robotics paper introduces F³, predictive event-based vision beyond optical flow — CSProfKGD · 2026-10-16
- VideoGen-Agent: An 8B Multimodal Agent Turns Video Generation Into a Tool-Use Loop — jiqizhixin · 2026-10-16
- Comprehension Audits: New Paper Proposes a Gate for AI-Written Code at Frontier Labs — ronbodkin · 2026-10-16
- Not Boring #215: Cammarata's Clean Networks Claim, Tesla's Flying Roadster, Tau Cut 73% — Not Boring (Packy McCormick) · 2026-10-16